2016 · 40 citations · 24 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureFault ToleranceFault-tolerant ComputingFault InjectionFault ModelingFault Tolerance DesignHardware Fault ToleranceReliable System DesignScalable Algorithm DesignChecksum AlgorithmsChecksum TechniquesFault Model AnalysisFault Tolerance MechanismsFault Tolerant AlgorithmsFault Tolerant ArchitecturesFault-tolerant ArchitectureScalability
Algorithm based fault tolerance (ABFT) attracts renewed interest for its extremely low overhead and good scalability. However the fault model used to design ABFT has been either abstract, simplistic, or both, leaving a gap between what occurs at the architecture level and what the algorithm expects. As the fault model is the deciding factor in choosing an effective checksum scheme, the resulting ABFT techniques have seen limited impact in practice. In this paper we seek to close the gap by directly using a comprehensive architectural fault model and devise a comprehensive ABFT scheme that can tolerate multiple architectural faults of various kinds. We implement the new ABFT scheme into high performance linpack (HPL) to demonstrate the feasibility in large scale high performance benchmark. We conduct architectural fault injection experiments and large scale experiments to empirically validate its fault tolerance and demonstrate the overhead of error handling, respectively.
24
Single event upset at ground level
E. Normand · IEEE Transactions on Nuclear Science · 1996 · 611 citations